I remember being at a conference where the editor for a major finance journal said of the “Russell reconstitution” quasi-experiment: “this design has been applied in so many places that we should either believes it affects everything on the planet, or nothing”

This same argument crops up any time an instrument gets popular. And imho it’s a very fair critique. Yet whenever a creative new instrument or quasi-exogenous shock comes out, it’s a mad dash for empiricists to go use that to study whatever outcome variable matters in their line of work

Amazing! Thanks for sharing

What does “just learning” mean? Do you mean it to contrast to other observational causal methods that propose assumptions (e.g. ignorability) that are put in place without data (or data verifiability)?

Broadcasters start selling “stoppage time” advertising.

FIFA advises stricter stoppage time accounting, yielding longer stoppage times.

💰💰💰

Tell your grandkids this was every day

the yolo approach

Great slide deck, thanks!

I am aware of papers where the graph is assumed to be known (e.g. arxiv.org/abs/2103.06392), and indeed I can construct one from the data that I have. But my concern is whether using the empirical graph ignores selection bias from customers choosing to form edges with certain products.

For outcomes, think of long-term customer spend, retail membership signup, or something else that is affected by the customer experience (the aggregate experience from products they interact with) but are not immediate consequences of a single product interaction.

Suppose an A/B test on a retail platform where products are randomly assigned into treatment or control, and outcomes are measured for customers. Edges are customer-product interactions (e.g. viewing a product). The treatment affects the desirability of the product, the likelihood it surfaces, etc.

it’s a weird partition of services: there’s a job board for serious folks and then a feed of cringey wannabe influencers peddling nonsense, phony inspirational stories, and infographics that remind you the difference between a left and right join as if that’s so freaking complicated

does this only work in december or can i put santa in a speedo out in july to signal my interest in having a neighborhood pool party

maybe exposure to the former drove demand for the latter, that’s how it works in my household

love matching my inks to my 3776s, they’re gorgeous pens

not sure how ergo it’d be to hit keys like “e”, seems like an awkward gesture

Slower is better. I left mastodon because it was just people relentlessly boosting the same posts I had already seen. Bluesky is small. We don’t need reposting. If your post was something I wanted to see, I’ll have seen it on one of my feeds already

first amendment activity is fine, it’s when things escalate to second amendment activity that things get dicey. if only we could get some meaningful regulation there